Alejo, L., Atkinson, J., Arriagada, C., Guzman-Fierro, V., & Roeckel, M. (2019). Effluent composition prediction of a two-stage anaerobic digestion process: machine learning and stoichiometry techniques (vol 25, pg 21149, 2018) (Vol. 26). Springer Heidelberg.
Abstract: The original publication of this paper contains a mistake. Unfortunately, an author was inadvertently missed out, Constanza Arriagada had participated in the operation of the anaerobic digesters cited in the work and now as a PhD student, she is involved in the production of other publication.
|
Alejo, L., Atkinson, J., Guzman-Fierro, V., & Roeckel, M. (2018). Effluent composition prediction of a two-stage anaerobic digestion process: machine learning and stoichiometry techniques. Environ. Sci. Pollut. Res., 25(21), 21149–21163.
Abstract: Computational self-adapting methods (Support Vector Machines, SVM) are compared with an analytical method in effluent composition prediction of a two-stage anaerobic digestion (AD) process. Experimental data for the AD of poultry manure were used. The analytical method considers the protein as the only source of ammonia production in AD after degradation. Total ammonia nitrogen (TAN), total solids (TS), chemical oxygen demand (COD), and total volatile solids (TVS) were measured in the influent and effluent of the process. The TAN concentration in the effluent was predicted, this being the most inhibiting and polluting compound in AD. Despite the limited data available, the SVM-based model outperformed the analytical method for the TAN prediction, achieving a relative average error of 15.2% against 43% for the analytical method. Moreover, SVM showed higher prediction accuracy in comparison with Artificial Neural Networks. This result reveals the future promise of SVM for prediction in non-linear and dynamic AD processes.
|
Alejo, L., Atkinson, J., & Lackner, S. (2020). Looking deeper – exploring hidden patterns in reactor data of N-removal systems through clustering analysis. Water Sci. Technol., 81(8), 1569–1577.
Abstract: In this work, clustering analysis of two partial nitritation-anammox (PN-A) moving bed biofilm reactors (MBBR) containing different types of carrier material was explored for the identification of patterns and operational conditions that may benefit process performance. The systems ran for two years under fluctuations of temperature and organic matter. Ex situ batch activity tests were performed every other week during the operation of these reactors. These datasets and the parameters, which were monitored online and in the laboratory, were combined and analyzed applying clustering analysis to identify non-obvious information regarding the performance of the systems. The initial results were consistent with the literature and from an operational perspective, which allowed the parameters to be explored further. The new information revealed that the oxidation reduction potential (ORP) and the anaerobic ammonium oxidizing bacteria (AnAOB) activity correlated well. ORP also dropped when the reactors were exposed to real wastewater (presence of organic matter). Moreover, operating conditions during nitrite accumulation were identified through clustering, and also revealed inhibition of anammox bacteria already at low nitrite concentrations.
|
Atkinson, J., & Escudero, A. (2022). Evolutionary natural-language coreference resolution for sentiment analysis. Int. J. Inf. Manage. Data Insights, 2(2), 100115.
Abstract: Communicating messages on social media usually conveys much implicit linguistic knowledge, which makes it difficult to process texts for further analysis. One of the major problems, the linguistic coreference resolution task involves detecting coreference chains of entities and pronouns that coreference them. It has mostly been addressed for formal and full-sized text in which a relatively clear discourse structure can be discovered, using Natural-Language Processing techniques. However, texts in social media are short, informal and lack a lot of underlying linguistic information to make decisions so traditional methods can not be applied. Furthermore, this may significantly impact the performance of several tasks on social media applications such as opinion mining, network analysis, sentiment analysis, text categorization. In order to deal with these issues, this research address the task of linguistic co-referencing using an evolutionary computation approach. It combines discourse coreference analysis techniques, domain-based heuristics (i.e., syntactic, semantic and world knowledge), graph representation methods, and evolutionary computation algorithms to resolving implicit co-referencing within informal opinion texts. Experiments were conducted to assess the ability of the model to find implicit referents on informal messages, showing the promise of our approach when compared to related methods.
|
Atkinson, J., & Maurelia, A. (2017). Redundancy-Based Trust in Question-Answering Systems. Computer, 50(1), 58–65.
Abstract: By combining user preferences, redundancy analysis, and trust-network inference, the proposed trust model can augment candidate answers with information about target sources on the basis of connections with other web users and sources. Experiments show that the model is more effective overall than trust analyses based on inference alone.
|
Figueroa, A., & Atkinson, J. (2019). Dual-View Learning for Detecting Web Query Intents. Computer, 52(8), 34–42.
Abstract: Automatically categorizing user intent behind web queries is a key issue not only for improving information retrieval tasks but also for designing tailored displays based on the underlying intention. In this article, a multiview learning method is proposed to recognize the user intent behind web searches.
|
Palma, D., & Atkinson, J. (2018). Coherence-Based Automatic Essay Assessment. IEEE Intell. Syst., 33(5), 26–36.
Abstract: In this paper, a discourse-based method that merges semantic and syntactic models for automated essay assessment is proposed. The approach combines shallow linguistic features and discourse patterns in order to predict an essay's score by using decision trees regression techniques. Unlike current approaches, our method directly measures an essay coherence by using corpus-based semantics and text centering techniques so as to determine discourse patterns underlying high-quality essays when compared with human assessed essays. Experiments using standard datasets showed that the proposed discourse-based approach outperformed traditional shallow features-based methods.
|
Reyes, D., & Atkinson, J. (2018). Person Re-identification Using Masked Keypoints. In Lecture Notes in Computer Sciences (Vol. 10868, pp. 45–56).
|